This pull request adds Llama Parse integration for complex document
parsing in Quivr. Llama Parse is a tool from Llama Index that allows you
to read complex documents in Quivr. It provides an API key that needs to
be added to the `.env` file as `LLAMA_CLOUD_API_KEY`. Once configured,
you can use the Llama Parse tool to read `pdf`, `docx`, and `doc` files
in Quivr.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
This pull request adds caching for the Supabase client and database
instances in order to improve performance and reduce unnecessary API
calls. The `get_supabase_client()` and `get_supabase_db()` functions now
check if the instances have already been created and return the cached
instances if available. This avoids creating new instances for every
function call, resulting in faster execution times.
This pull request adds the pyinstrument package and updates the Makefile
and backend code. The pyinstrument package is used for profiling and the
Makefile and backend code have been modified to support profiling.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
This pull request adds a ci-migration script that sets the project ID
from an environment variable and runs the supabase link and supabase db
push commands. This script will be used for continuous integration
purposes.
This pull request removes the citation metadata from the generate_answer
and generate_stream functions. The citation metadata was previously
being added to the streamed_chat_history and metadata dictionaries, but
it is no longer necessary. This change improves the efficiency and
clarity of the code.
This pull request updates the chunk size and overlap parameters in the
File class to improve performance. It also increases the top_n value in
the compressor for both the CohereRerank and FlashrankRerank models.
Additionally, it ensures that the page content is encoded in UTF-8
before processing.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
This pull request updates the Dockerfile to include the installation of
the Supabase CLI. The Supabase CLI is required for interacting with the
Supabase backend. This update ensures that the Supabase CLI is installed
in the Docker image, allowing developers to easily use the Supabase CLI
within their Docker environment.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
… to the DB API
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
This pull request updates the chunk overlap value in the File class from
300 to 200. This change reduces the overlap between chunks, improving
the performance of chunking operations.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
This pull request adds the flashrank and contextual compression
retriever to the codebase. The flashrank reranker model is used for
compression, and the contextual compression retriever combines the base
compressor and base retriever to improve document retrieval.
This pull request updates the API documentation to include new sections
on configuring Quivr and contacting the Quivr team. It also removes the
"API Brains" section from the documentation.
This pull request fixes the issue of duplicate sources in the model
response and adds metadata to the response. It removes duplicate sources
with the same name and creates a list of unique sources. Additionally,
it includes the generated URLs and sources in the metadata of the model
response.
This pull request refactors the GPT4Brain and KnowledgeBrainQA classes
to add the functionality of saving non-streaming answers. It includes
changes to the `generate_answer` method and the addition of the
`save_non_streaming_answer` method. This enhancement improves the
overall functionality and performance of the code.
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
<!--
ELLIPSIS_HIDDEN
-->
----
| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
997576d577 |
|--------|
### Summary:
This PR involves a significant refactoring of the codebase, with file
and class relocations and renames, and updated import paths, without
introducing new functionality.
**Key points**:
- Significant refactoring of the codebase for improved organization and
clarity.
- File and class relocations and renames.
- Updated import paths to reflect new locations and names.
- No new functionality introduced.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
# Description
Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.
## Checklist before requesting a review
Please delete options that are not relevant.
- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged
## Screenshots (if appropriate):
<!--
ELLIPSIS_HIDDEN
-->
----
| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
3e95f1a5aa |
|--------|
### Summary:
This PR introduces the 'Quivr Assistants' feature with new frontend
components and pages, backend routes and DTOs changes, and a minor
update in the `processAssistant` function.
**Key points**:
- Introduced the 'Quivr Assistants' feature with new frontend components
and pages, backend routes and DTOs changes.
- Added new `AssistantModal` component in
`/frontend/app/assistants/AssistantModal/AssistantModal.tsx`.
- Added new `InputsStep` and `OutputsStep` components for handling
assistant inputs and outputs.
- Added new `AssistantModal` page in
`/frontend/app/assistants/page.tsx`.
- Added new API endpoints and types for assistants in
`/frontend/lib/api/assistants/assistants.ts` and
`/frontend/lib/api/assistants/types.ts`.
- Updated backend assistant routes and DTOs in
`backend/modules/assistant/controller/assistant_routes.py`,
`backend/modules/assistant/dto/inputs.py`,
`backend/modules/assistant/ito/difference.py`, and
`backend/modules/assistant/ito/summary.py`.
- Made a minor update in the `processAssistant` function in the
`/frontend/lib/api/assistants/assistants.ts` file.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
This pull request includes a commit that improves the prompt used to get
more insights from the document. The commit modifies the map and reduce
templates to provide clearer instructions for analyzing each section of
the document and generating a consolidated summary. The changes also
include adjustments to the text splitter to improve the chunk overlap.
<!--
ELLIPSIS_HIDDEN
-->
----
| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
adf5541dab |
|--------|
### Summary:
This PR enhances the document analysis and summary generation
instructions in the `SummaryAssistant` class and improves text splitting
by adjusting the `chunk_overlap` parameter.
**Key points**:
- Updated `map_template` and `reduce_template` in `process_assistant`
method of `SummaryAssistant` class in
`/backend/modules/assistant/ito/summary.py`.
- Adjusted `chunk_overlap` parameter of `CharacterTextSplitter` instance
from 0 to 100.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
This pull request fixes an issue where the brain activation and value
handling were not working correctly. The `BrainInput` model now allows
for optional activation and value fields, and an empty string is
converted to `None` using a root validator. This ensures that brain
activation and value can be properly handled in the application.
<!--
ELLIPSIS_HIDDEN
-->
----
| 🚀 This description was created by
[Ellipsis](https://www.ellipsis.dev) for commit
d63ed6e651 |
|--------|
### Summary:
This PR modifies the `BrainInput` class in
`/backend/modules/assistant/dto/inputs.py` to make `activated` and
`value` fields optional and adds a root validator to convert empty
strings to `None`.
**Key points**:
- Modified `BrainInput` class in
`/backend/modules/assistant/dto/inputs.py`
- Made `activated` and `value` fields optional with default values
- Added root validator `empty_string_to_none` to convert empty strings
to `None`
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
This pull request refactors the DEFAULT_DOCUMENT_PROMPT in quivr_rag.py
to improve code readability and maintainability. The unnecessary file
name information has been removed from the prompt template as it is now
included in the vector embedding
<!--
ELLIPSIS_HIDDEN
-->
----
| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 81939457e6. |
|--------|--------|
### Summary:
This PR refactors the `DEFAULT_DOCUMENT_PROMPT` in `quivr_rag.py` by
removing the file name information from the prompt template, enhancing
code readability and maintainability.
**Key points**:
- Refactored `DEFAULT_DOCUMENT_PROMPT` in `quivr_rag.py`.
- Removed file name information from the prompt template.
- File name information is now included in the vector embedding.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
This pull request fixes the file key validation in the `check_input`
method. Previously, the method only checked if a file was uploaded and
if the key of the file was "doc_to_summarize". However, it did not check
if the key of the file was the same as the name of the file. This PR
adds a check to ensure that the key of the file is the same as the name
of the file. This improves the accuracy of the file validation process.
<!--
ELLIPSIS_HIDDEN
-->
----
| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 8f04d832ac. |
|--------|--------|
### Summary:
This PR enhances the file validation process in the `SummaryAssistant`
class by ensuring the key of the uploaded file matches its filename.
**Key points**:
- Added a new file key validation in `check_input` method of
`SummaryAssistant` class.
- The validation checks if the key of the uploaded file matches the
filename.
- This is an additional check to the existing file upload and key
validations.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
This pull request increases the token limit for the summary output to
2000 in order to accommodate larger documents.
<!--
ELLIPSIS_HIDDEN
-->
----
| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit 4412ecde83. |
|--------|--------|
### Summary:
This PR increases the token limit for the summary output to 2000 in the
`SummaryAssistant` class to accommodate larger documents.
**Key points**:
- Increased `max_tokens` parameter in `ChatLiteLLM` instance to 2000 in
`process_assistant` function of `SummaryAssistant` class in
`/backend/modules/assistant/ito/summary.py` file.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
This pull request refactors the get_brains_usages method in the
Analytics class. The changes include improving code readability,
optimizing database queries, and fixing potential bugs.
<!--
ELLIPSIS_HIDDEN
-->
----
| <a href="https://ellipsis.dev" target="_blank"><img
src="https://avatars.githubusercontent.com/u/80834858?s=400&u=31e596315b0d8f7465b3ee670f25cea677299c96&v=4"
alt="Ellipsis" width="30px" height="30px"/></a> | 🚀 This PR
description was created by [Ellipsis](https://www.ellipsis.dev) for
commit f0ad664673. |
|--------|--------|
### Summary:
This PR optimizes the `get_brains_usages` method in the `Analytics`
class by reducing database calls and improving code readability.
**Key points**:
- Refactored `get_brains_usages` method in `Analytics` class.
- Optimized database query to fetch chat history in one go.
- Improved code readability and formatting.
----
Generated with ❤️ by [ellipsis.dev](https://www.ellipsis.dev)
<!--
ELLIPSIS_HIDDEN
-->
